Meta-learning
Meta-Learning is a subfield of machine learning that focuses on designing algorithms capable of learning how to learn, enabling models to generalize across tasks by acquiring inductive biases from prior experience.
3.3K
Publications
224.9K
Citations
10.2K
Authors
2.1K
Institutions
Publications per year
2017–2026
2.7K
3.3K
A survey on Image Data Augmentation for Deep Learning
Connor Shorten, Taghi M. Khoshgoftaar · Journal Of Big Data · 2019 · 12.4K citations · Full text
Prototypical Networks for Few-shot Learning
Jake Snell, Kevin Swersky, Richard S. Zemel · arXiv (Cornell University) · 2017 · 5.2K citations · Full text
A few useful things to know about machine learning
Pedro Domingos · Communications of the ACM · 2012 · 3.2K citations
1–5 of 3.3K
10.2K
27
h-index
27
h-index
21
h-index
18
h-index
15
h-index
1–5 of 10.2K
2.1K
Google (United States)
Mountain View, United States
40 h-index
252 publications
23.4K citations
Tsinghua University
Beijing, China
38 h-index
177 publications
12.2K citations
University of California, Berkeley
Berkeley, United States
38 h-index
128 publications
39.4K citations

Chinese Academy of Sciences
Beijing, China
35 h-index
184 publications
8.8K citations
Nanyang Technological University
Singapore, Singapore
32 h-index
124 publications
10.4K citations

Shanghai Jiao Tong University
Shanghai, China
29 h-index
147 publications
9.9K citations

Xi'an Jiaotong University
Xi'an, China
28 h-index
133 publications
11K citations
Carnegie Mellon University
Pittsburgh, United States
28 h-index
102 publications
7.3K citations
1–8 of 2.1K
Repository · 539 publications · 42K citations
83
h-index
Conference · 83 publications · 6.9K citations
41
h-index
64 publications · 2.4K citations
30
h-index
TPAMI · 35 publications · 3.6K citations
27
h-index
43 publications · 3.3K citations
27
h-index
1–5